Alert button
Picture for Zheng Xu

Zheng Xu

Alert button

Privacy-Preserving Instructions for Aligning Large Language Models

Feb 21, 2024
Da Yu, Peter Kairouz, Sewoong Oh, Zheng Xu

Viaarxiv icon

PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter

Feb 16, 2024
Junfei Xiao, Zheng Xu, Alan Yuille, Shen Yan, Boyu Wang

Viaarxiv icon

Heterogeneous Low-Rank Approximation for Federated Fine-tuning of On-Device Foundation Models

Jan 12, 2024
Yae Jee Cho, Luyang Liu, Zheng Xu, Aldi Fahrezi, Gauri Joshi

Viaarxiv icon

InstructPipe: Building Visual Programming Pipelines with Human Instructions

Dec 15, 2023
Zhongyi Zhou, Jing Jin, Vrushank Phadnis, Xiuxiu Yuan, Jun Jiang, Xun Qian, Jingtao Zhou, Yiyi Huang, Zheng Xu, Yinda Zhang, Kristen Wright, Jason Mayes, Mark Sherwood, Johnny Lee, Alex Olwal, David Kim, Ram Iyengar, Na Li, Ruofei Du

Viaarxiv icon

Analyze Drivers' Intervention Behavior During Autonomous Driving -- A VR-incorporated Approach

Dec 04, 2023
Zheng Xu

Viaarxiv icon

User Inference Attacks on Large Language Models

Oct 13, 2023
Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu

Figure 1 for User Inference Attacks on Large Language Models
Figure 2 for User Inference Attacks on Large Language Models
Figure 3 for User Inference Attacks on Large Language Models
Figure 4 for User Inference Attacks on Large Language Models
Viaarxiv icon

(Amplified) Banded Matrix Factorization: A unified approach to private training

Jun 13, 2023
Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, Keith Rush, Abhradeep Guha Thakurta, Zheng Xu

Figure 1 for (Amplified) Banded Matrix Factorization: A unified approach to private training
Figure 2 for (Amplified) Banded Matrix Factorization: A unified approach to private training
Figure 3 for (Amplified) Banded Matrix Factorization: A unified approach to private training
Figure 4 for (Amplified) Banded Matrix Factorization: A unified approach to private training
Viaarxiv icon

Federated Learning of Gboard Language Models with Differential Privacy

May 29, 2023
Zheng Xu, Yanxiang Zhang, Galen Andrew, Christopher A. Choquette-Choo, Peter Kairouz, H. Brendan McMahan, Jesse Rosenstock, Yuanbo Zhang

Figure 1 for Federated Learning of Gboard Language Models with Differential Privacy
Figure 2 for Federated Learning of Gboard Language Models with Differential Privacy
Figure 3 for Federated Learning of Gboard Language Models with Differential Privacy
Figure 4 for Federated Learning of Gboard Language Models with Differential Privacy
Viaarxiv icon

Can Public Large Language Models Help Private Cross-device Federated Learning?

May 20, 2023
Boxin Wang, Yibo Jacky Zhang, Yuan Cao, Bo Li, H. Brendan McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

Figure 1 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 2 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 3 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Figure 4 for Can Public Large Language Models Help Private Cross-device Federated Learning?
Viaarxiv icon

An Empirical Evaluation of Federated Contextual Bandit Algorithms

Mar 17, 2023
Alekh Agarwal, H. Brendan McMahan, Zheng Xu

Figure 1 for An Empirical Evaluation of Federated Contextual Bandit Algorithms
Figure 2 for An Empirical Evaluation of Federated Contextual Bandit Algorithms
Figure 3 for An Empirical Evaluation of Federated Contextual Bandit Algorithms
Figure 4 for An Empirical Evaluation of Federated Contextual Bandit Algorithms
Viaarxiv icon